The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install the @membranehq/cli package globally via npm. This is a legitimate utility provided by the skill author (membranedev) to manage integrations.
[COMMAND_EXECUTION]: The skill operates by executing shell commands using the membrane CLI. These commands handle authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). All command patterns are consistent with the intended functionality.
[SAFE]: Indirect Prompt Injection Surface Analysis:
Ingestion points: The skill fetches external content such as posts, comments, and user data from Beekeeper via actions like list-posts and list-comments as described in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded instructions are provided in the documentation.
Capability inventory: The skill possesses write capabilities including create-post, update-user, and send-message across its documented actions.
Sanitization: No explicit mention of input sanitization for external content is provided; however, as this is a standard integration tool, the risk is considered inherent to the primary purpose.

beekeeper